{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:40:03Z","timestamp":1777063203123,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9\u2009minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose &gt;180\u2009mg\/dL) by 10.8% (<jats:italic>P<\/jats:italic>\u2009=\u20090.04) and trends toward increasing time in range (70\u2013180\u2009mg\/dL) by 9.1% compared with MPC. Time below range (glucose &lt;70\u2009mg\/dL) is not significantly different between RAP and MPC.<\/jats:p>","DOI":"10.1038\/s41746-023-00783-1","type":"journal-article","created":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T19:41:17Z","timestamp":1679859677000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1586-2490","authenticated-orcid":false,"given":"Clara","family":"Mosquera-Lopez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3634-481X","authenticated-orcid":false,"given":"Leah M.","family":"Wilson","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"El Youssef","sequence":"additional","affiliation":[]},{"given":"Wade","family":"Hilts","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5434-9361","authenticated-orcid":false,"given":"Joseph","family":"Leitschuh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2822-587X","authenticated-orcid":false,"given":"Deborah","family":"Branigan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6256-9938","authenticated-orcid":false,"given":"Virginia","family":"Gabo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0319-255X","authenticated-orcid":false,"given":"Jae H.","family":"Eom","sequence":"additional","affiliation":[]},{"given":"Jessica R.","family":"Castle","sequence":"additional","affiliation":[]},{"given":"Peter G.","family":"Jacobs","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"783_CR1","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/S2213-8587(21)00289-8","volume":"10","author":"LM Wilson","year":"2022","unstructured":"Wilson, L. M., Jacobs, P. G., Riddell, M. C., Zaharieva, D. P. & Castle, J. R. Opportunities and challenges in closed-loop systems in type 1 diabetes. Lancet Diabetes Endocrinol. 10, 6\u20138 (2022).","journal-title":"Lancet Diabetes Endocrinol."},{"key":"783_CR2","doi-asserted-by":"publisher","first-page":"100312","DOI":"10.1016\/j.cobme.2021.100312","volume":"19","author":"EM Aiello","year":"2021","unstructured":"Aiello, E. M. et al. Review of automated insulin delivery systems for individuals with type 1 diabetes: tailored solutions for subpopulations. Curr. Opin. Biomed. Eng. 19, 100312 (2021).","journal-title":"Curr. Opin. Biomed. Eng."},{"key":"783_CR3","doi-asserted-by":"publisher","first-page":"E689","DOI":"10.1016\/S2589-7500(21)00218-1","volume":"3","author":"CK Boughton","year":"2021","unstructured":"Boughton, C. K. Fully closed-loop insulin delivery\u2014are we nearly there yet? Lancet Digital Health 3, E689\u2013E690 (2021).","journal-title":"Lancet Digital Health"},{"key":"783_CR4","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1089\/dia.2020.0357","volume":"23","author":"MB Gillingham","year":"2021","unstructured":"Gillingham, M. B. et al. Assessing mealtime macronutrient content: patient perceptions versus expert analyses via a novel phone app. Diabetes Technol. Ther. 23, 85\u201394 (2021).","journal-title":"Diabetes Technol. Ther."},{"key":"783_CR5","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1177\/1932296816679850","volume":"11","author":"A Deeb","year":"2017","unstructured":"Deeb, A., Al Hajeri, A., Alhmoudi, I. & Nagelkerke, N. Accurate carbohydrate counting is an important determinant of postprandial glycemia in children and adolescents with type 1 diabetes on insulin pump therapy. J. Diabetes Sci. Technol. 11, 753\u2013758 (2017).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR6","doi-asserted-by":"publisher","first-page":"823","DOI":"10.2337\/dc10-1490","volume":"34","author":"A Laurenzi","year":"2011","unstructured":"Laurenzi, A. et al. Effects of carbohydrate counting on glucose control and quality of life over 24 weeks in adult patients with type 1 diabetes on continuous subcutaneous insulin infusion: a randomized, prospective clinical trial (GIOCAR). Diabetes Care 34, 823\u2013827 (2011).","journal-title":"Diabetes Care"},{"key":"783_CR7","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1109\/JBHI.2017.2677953","volume":"21","author":"S Samadi","year":"2017","unstructured":"Samadi, S. et al. Meal detection and carbohydrate estimation using continuous glucose sensor data. IEEE J. Biomed. Health Inform. 21, 619\u2013627 (2017).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"783_CR8","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/JBHI.2015.2446413","volume":"20","author":"K Turksoy","year":"2016","unstructured":"Turksoy, K. et al. Meal detection in patients with type 1 diabetes: a new module for the multivariable adaptive artificial pancreas control system. IEEE J. Biomed. Health Inform. 20, 47\u201354 (2016).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"783_CR9","doi-asserted-by":"publisher","first-page":"295","DOI":"10.2337\/dc07-1293","volume":"31","author":"E Dassau","year":"2008","unstructured":"Dassau, E., Bequette, B. W., Buckingham, B. A. & Doyle, F. J. 3rd Detection of a meal using continuous glucose monitoring: implications for an artificial beta-cell. Diabetes Care 31, 295\u2013300 (2008).","journal-title":"Diabetes Care"},{"key":"783_CR10","doi-asserted-by":"publisher","first-page":"884","DOI":"10.3390\/s18030884","volume":"18","author":"CM Ramkissoon","year":"2018","unstructured":"Ramkissoon, C. M., Herrero, P., Bondia, J. & Vehi, J. Unannounced meals in the artificial pancreas: detection using continuous glucose monitoring. Sensors (Basel) 18, 884 (2018).","journal-title":"Sensors (Basel)"},{"key":"783_CR11","doi-asserted-by":"publisher","first-page":"106736","DOI":"10.1016\/j.cmpb.2022.106736","volume":"219","author":"S Faccioli","year":"2022","unstructured":"Faccioli, S. et al. Super-twisting-based meal detector for type 1 diabetes management: Improvement and assessment in a real-life scenario. Comput. Methods Prog. Biomed. 219, 106736 (2022).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"783_CR12","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1089\/dia.2017.0078","volume":"19","author":"FM Cameron","year":"2017","unstructured":"Cameron, F. M. et al. Closed-loop control without meal announcement in type 1 diabetes. Diabetes Technol. Ther. 19, 527\u2013532 (2017).","journal-title":"Diabetes Technol. Ther."},{"key":"783_CR13","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1109\/TBME.2020.3004270","volume":"68","author":"L Meneghetti","year":"2021","unstructured":"Meneghetti, L., Facchinetti, A. & Favero, S. D. Model-based detection and classification of insulin pump faults and missed meal announcements in artificial pancreas systems for type 1 diabetes therapy. IEEE Trans. Biomed. Eng. 68, 170\u2013180 (2021).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"783_CR14","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1177\/1932296814523881","volume":"8","author":"RA Harvey","year":"2014","unstructured":"Harvey, R. A., Dassau, E., Zisser, H., Seborg, D. E. & Doyle, F. J. 3rd Design of the glucose rate increase detector: a meal detection module for the health monitoring system. J. Diabetes Sci. Technol. 8, 307\u2013320 (2014).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR15","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.1111\/dom.14737","volume":"24","author":"JP Corbett","year":"2022","unstructured":"Corbett, J. P. et al. Smartwatch gesture-based meal reminders improve glycaemic control. Diabetes Obes. Metab. 24, 1667\u20131670 (2022).","journal-title":"Diabetes Obes. Metab."},{"key":"783_CR16","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1177\/19322968211059159","volume":"16","author":"JP Corbett","year":"2022","unstructured":"Corbett, J. P., Garcia-Tirado, J., Colmegna, P., Diaz Castaneda, J. L. & Breton, M. D. Using an online disturbance rejection and anticipation system to reduce hyperglycemia in a fully closed-loop artificial pancreas system. J. Diabetes Sci. Technol. 16, 52\u201360 (2022).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR17","doi-asserted-by":"publisher","first-page":"e723","DOI":"10.1016\/S2589-7500(21)00139-4","volume":"3","author":"MA Tsoukas","year":"2021","unstructured":"Tsoukas, M. A. et al. A fully artificial pancreas versus a hybrid artificial pancreas for type 1 diabetes: a single-centre, open-label, randomised controlled, crossover, non-inferiority trial. Lancet Digit Health 3, e723\u2013e732 (2021).","journal-title":"Lancet Digit Health"},{"key":"783_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10273660008833060","volume":"3","author":"BP Kovatchev","year":"2000","unstructured":"Kovatchev, B. P., Straume, M., Cox, D. J. & Farhy, L. S. Risk analysis of blood glucose data: a quantitative approach to optimizing the control of insulin dependent diabetes. J. Theor. Med. 3, 1\u201310 (2000).","journal-title":"J. Theor. Med."},{"key":"783_CR19","doi-asserted-by":"publisher","first-page":"e0217301","DOI":"10.1371\/journal.pone.0217301","volume":"14","author":"N Resalat","year":"2019","unstructured":"Resalat, N., El Youssef, J., Tyler, N., Castle, J. & Jacobs, P. G. A statistical virtual patient population for the glucoregulatory system in type 1 diabetes with integrated exercise model. PLoS One 14, e0217301 (2019).","journal-title":"PLoS One"},{"key":"783_CR20","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.2337\/dc18-0228","volume":"41","author":"JR Castle","year":"2018","unstructured":"Castle, J. R. et al. Randomized outpatient trial of single- and dual-hormone closed-loop systems that adapt to exercise using wearable sensors. Diabetes Care. 41, 1471\u20131477 (2018).","journal-title":"Diabetes Care."},{"key":"783_CR21","first-page":"2270","volume":"2016","author":"N Resalat","year":"2016","unstructured":"Resalat, N., El Youssef, J., Reddy, R. & Jacobs, P. G. Design of a dual-hormone model predictive control for artificial pancreas with exercise model. Annu. Int Conf. IEEE Eng. Med. Biol. Soc. 2016, 2270\u20132273 (2016).","journal-title":"Annu. Int Conf. IEEE Eng. Med. Biol. Soc."},{"key":"783_CR22","doi-asserted-by":"publisher","first-page":"2569","DOI":"10.1109\/TBME.2014.2323248","volume":"61","author":"PG Jacobs","year":"2014","unstructured":"Jacobs, P. G. et al. Automated control of an adaptive bihormonal, dual-sensor artificial pancreas and evaluation during inpatient studies. IEEE Trans. Biomed. Eng. 61, 2569\u20132581 (2014).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"783_CR23","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1177\/1932296815609371","volume":"9","author":"PG Jacobs","year":"2015","unstructured":"Jacobs, P. G. et al. Incorporating an exercise detection, grading, and hormone dosing algorithm into the artificial pancreas using accelerometry and heart rate. J. Diabetes Sci. Technol. 9, 1175\u20131184 (2015).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR24","doi-asserted-by":"crossref","unstructured":"Mosquera-Lopez, C. & Jacobs, P. G. Incorporating glucose variability into glucose forecasting accuracy assessment using the new glucose variability impact index and the prediction consistency index: an LSTM case example. J. Diabetes Sci. Technol. 16, 7\u201318 (2021).","DOI":"10.1177\/19322968211042621"},{"key":"783_CR25","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Paper presented at: 13th Int. Conf. Artificial Intelligence and Statistics (2010)."},{"key":"783_CR26","unstructured":"Kingma, D. & Ba, J. Adam: a method for stochastic optimization. In Paper presented at: 3rd Int. Conf. for Learning Representations (2015)."},{"key":"783_CR27","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1088\/0967-3334\/25\/4\/010","volume":"25","author":"R Hovorka","year":"2004","unstructured":"Hovorka, R. et al. Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes. Physiol. Meas. 25, 905\u2013920 (2004).","journal-title":"Physiol. Meas."},{"key":"783_CR28","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1177\/193229680700100603","volume":"1","author":"L Magni","year":"2007","unstructured":"Magni, L. et al. Model predictive control of type 1 diabetes: an in silico trial. J. Diabetes Sci. Technol. 1, 804\u2013812 (2007).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR29","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1177\/193229681000400611","volume":"4","author":"B Kovatchev","year":"2010","unstructured":"Kovatchev, B. et al. Multinational study of subcutaneous model-predictive closed-loop control in type 1 diabetes mellitus: summary of the results. J. Diabetes Sci. Technol. 4, 1374\u20131381 (2010).","journal-title":"J. Diabetes Sci. Technol."},{"key":"783_CR30","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.2337\/dc13-1631","volume":"37","author":"S Del Favero","year":"2014","unstructured":"Del Favero, S. et al. First use of model predictive control in outpatient wearable artificial pancreas. Diabetes Care. 37, 1212\u20131215 (2014).","journal-title":"Diabetes Care."},{"key":"783_CR31","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1111\/dom.12440","volume":"17","author":"S Del Favero","year":"2015","unstructured":"Del Favero, S. et al. Multicenter outpatient dinner\/overnight reduction of hypoglycemia and increased time of glucose in target with a wearable artificial pancreas using modular model predictive control in adults with type 1 diabetes. Diabetes Obes. Metab. 17, 468\u2013476 (2015).","journal-title":"Diabetes Obes. Metab."},{"key":"783_CR32","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1016\/S2213-8587(15)00335-6","volume":"3","author":"J Kropff","year":"2015","unstructured":"Kropff, J. et al. 2 month evening and night closed-loop glucose control in patients with type 1 diabetes under free-living conditions: a randomised crossover trial. Lancet Diabetes Endocrinol. 3, 939\u2013947 (2015).","journal-title":"Lancet Diabetes Endocrinol."},{"key":"783_CR33","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1056\/NEJMoa1509351","volume":"373","author":"H Thabit","year":"2015","unstructured":"Thabit, H. et al. Home use of an artificial beta cell in type 1 diabetes. N. Engl. J. Med. 373, 2129\u20132140 (2015).","journal-title":"N. Engl. J. Med."},{"key":"783_CR34","doi-asserted-by":"publisher","first-page":"2721","DOI":"10.2337\/dc19-2267","volume":"43","author":"LM Wilson","year":"2020","unstructured":"Wilson, L. M. et al. Dual-hormone closed-loop system using a liquid stable glucagon formulation versus insulin-only closed-loop system compared with a predictive low glucose suspend system: an open-label, outpatient, single-center, crossover, randomized controlled trial. Diabetes Care. 43, 2721\u20132729 (2020).","journal-title":"Diabetes Care."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00783-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00783-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00783-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T19:41:33Z","timestamp":1679859693000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00783-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["783"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00783-1","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"15 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"P.G.J. and J.R.C. have a financial interest in Pacific Diabetes Technologies Inc., a company that may have a commercial interest in the results of this research and technology. J.R.C. also reports advisory board participation for Zealand Pharma, Novo Nordisk, Insulet, and AstraZeneca, and her institution has received research funding from Dexcom. For all other authors, no competing interests exist.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"39"}}